Determining the similarity of deformable shapes

Ronen Basri, Luiz Costa, Davi Geiger, David Jacobs

Research output: Contribution to journalArticle

Abstract

Determining the similarity of two shapes is a significant task in both machine and human vision systems that must recognize or classify objects. The exact properties of human shape similarity judgements are not well understood yet, and this task is particularly difficult in domains where the shapes are not related by rigid transformations. In this paper we identify a number of possibly desirable properties of a shape similarity method, and determine the extent to which these properties can be captured by approaches that compare local properties of the contours of the shapes, through elastic matching. Special attention is devoted to objects that possess articulations, i.e. articulated parts. Elastic matching evaluates the similarity of two shapes as the sum of local deformations needed to change one shape into another. We show that similarities of part structure can be captured by such an approach, without the explicit computation of part structure. This may be of importance, since although parts appear to play a significant role in visual recognition, it is difficult to stably determine part structure. We also show novel results about how one can evaluate smooth and polyhedral shapes with the same method. Finally, we describe shape similarity effects that cannot be handled by current approaches.

Original languageEnglish (US)
Pages (from-to)2365-2385
Number of pages21
JournalVision Research
Volume38
Issue number15-16
DOIs
StatePublished - Aug 1998

Fingerprint

Recognition (Psychology)

ASJC Scopus subject areas

  • Ophthalmology
  • Sensory Systems

Cite this

Determining the similarity of deformable shapes. / Basri, Ronen; Costa, Luiz; Geiger, Davi; Jacobs, David.

In: Vision Research, Vol. 38, No. 15-16, 08.1998, p. 2365-2385.

Research output: Contribution to journalArticle

Basri, Ronen ; Costa, Luiz ; Geiger, Davi ; Jacobs, David. / Determining the similarity of deformable shapes. In: Vision Research. 1998 ; Vol. 38, No. 15-16. pp. 2365-2385.
@article{4e8af1a77e894dbeb6017a01004944d9,
title = "Determining the similarity of deformable shapes",
abstract = "Determining the similarity of two shapes is a significant task in both machine and human vision systems that must recognize or classify objects. The exact properties of human shape similarity judgements are not well understood yet, and this task is particularly difficult in domains where the shapes are not related by rigid transformations. In this paper we identify a number of possibly desirable properties of a shape similarity method, and determine the extent to which these properties can be captured by approaches that compare local properties of the contours of the shapes, through elastic matching. Special attention is devoted to objects that possess articulations, i.e. articulated parts. Elastic matching evaluates the similarity of two shapes as the sum of local deformations needed to change one shape into another. We show that similarities of part structure can be captured by such an approach, without the explicit computation of part structure. This may be of importance, since although parts appear to play a significant role in visual recognition, it is difficult to stably determine part structure. We also show novel results about how one can evaluate smooth and polyhedral shapes with the same method. Finally, we describe shape similarity effects that cannot be handled by current approaches.",
author = "Ronen Basri and Luiz Costa and Davi Geiger and David Jacobs",
year = "1998",
month = "8",
doi = "10.1016/S0042-6989(98)00043-1",
language = "English (US)",
volume = "38",
pages = "2365--2385",
journal = "Vision Research",
issn = "0042-6989",
publisher = "Elsevier Limited",
number = "15-16",

}

TY - JOUR

T1 - Determining the similarity of deformable shapes

AU - Basri, Ronen

AU - Costa, Luiz

AU - Geiger, Davi

AU - Jacobs, David

PY - 1998/8

Y1 - 1998/8

N2 - Determining the similarity of two shapes is a significant task in both machine and human vision systems that must recognize or classify objects. The exact properties of human shape similarity judgements are not well understood yet, and this task is particularly difficult in domains where the shapes are not related by rigid transformations. In this paper we identify a number of possibly desirable properties of a shape similarity method, and determine the extent to which these properties can be captured by approaches that compare local properties of the contours of the shapes, through elastic matching. Special attention is devoted to objects that possess articulations, i.e. articulated parts. Elastic matching evaluates the similarity of two shapes as the sum of local deformations needed to change one shape into another. We show that similarities of part structure can be captured by such an approach, without the explicit computation of part structure. This may be of importance, since although parts appear to play a significant role in visual recognition, it is difficult to stably determine part structure. We also show novel results about how one can evaluate smooth and polyhedral shapes with the same method. Finally, we describe shape similarity effects that cannot be handled by current approaches.

AB - Determining the similarity of two shapes is a significant task in both machine and human vision systems that must recognize or classify objects. The exact properties of human shape similarity judgements are not well understood yet, and this task is particularly difficult in domains where the shapes are not related by rigid transformations. In this paper we identify a number of possibly desirable properties of a shape similarity method, and determine the extent to which these properties can be captured by approaches that compare local properties of the contours of the shapes, through elastic matching. Special attention is devoted to objects that possess articulations, i.e. articulated parts. Elastic matching evaluates the similarity of two shapes as the sum of local deformations needed to change one shape into another. We show that similarities of part structure can be captured by such an approach, without the explicit computation of part structure. This may be of importance, since although parts appear to play a significant role in visual recognition, it is difficult to stably determine part structure. We also show novel results about how one can evaluate smooth and polyhedral shapes with the same method. Finally, we describe shape similarity effects that cannot be handled by current approaches.

UR - http://www.scopus.com/inward/record.url?scp=0031875453&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031875453&partnerID=8YFLogxK

U2 - 10.1016/S0042-6989(98)00043-1

DO - 10.1016/S0042-6989(98)00043-1

M3 - Article

C2 - 9798005

AN - SCOPUS:0031875453

VL - 38

SP - 2365

EP - 2385

JO - Vision Research

JF - Vision Research

SN - 0042-6989

IS - 15-16

ER -